Search Results for author:
Found 64 papers, 22 papers with code
Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
Recently, reinforcement learning (RL)-based tuning has shifted the trajectory of Multimodal Large Language Models (MLLMs), particularly following the introduction of Group Relative Policy Optimization (GRPO).
DRA-GRPO: Exploring Diversity-Aware Reward Adjustment for R1-Zero-Like Training of Large Language Models
Our method integrates seamlessly with both GRPO and its variant DR.~GRPO, resulting in $\textit{DRA-GRPO}$ and $\textit{DGA-DR.~GRPO}$.
FIC-TSC: Learning Time Series Classification with Fisher Information Constraint
However, there is a large consensus that time series data often suffers from domain shifts between training and test sets, which dramatically degrades the classification performance.
Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
Medical question answering (QA) is a reasoning-intensive task that remains challenging for large language models (LLMs) due to hallucinations and outdated domain knowledge.
How Effective Can Dropout Be in Multiple Instance Learning ?
Due to the gigapixel resolution of WSI, applications of MIL in WSI typically necessitate a two-stage training scheme: first, extract features from the pre-trained backbone and then perform MIL aggregation.
Schrödinger Diffusion Driven Signal Recovery in 3T BOLD fMRI Using Unmatched 7T Observations
Ultra-high-field (7 Tesla) BOLD fMRI offers exceptional detail in both spatial and temporal domains, along with robust signal-to-noise characteristics, making it a powerful modality for studying visual information processing in the brain.
Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation
Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks.
Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes
In addition, we showed that the model was also generalizable to the brain amyloid positivity prediction with individuals in the medium risk class, where BM alone cannot achieve a clear classification.
EyeBench: A Call for More Rigorous Evaluation of Retinal Image Enhancement
To this end, we propose a novel comprehensive benchmark, EyeBench, to provide insights that align enhancement models with clinical needs, offering a foundation for future work to improve the clinical relevance and applicability of generative models for fundus image enhancement.
Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
Since its introduction, the transformer has shifted the development trajectory away from traditional models (e. g., RNN, MLP) in time series forecasting, which is attributed to its ability to capture global dependencies within temporal tokens.
Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN
In this paper, we performed a thorough study on the effect of incorporating BBBM into deep generative models.
Multimodal Variational Autoencoder: a Barycentric View
Previous attempts at multimodal VAEs approach this mainly through the lens of experts, aggregating unimodal inference distributions with a product of experts (PoE), a mixture of experts (MoE), or a combination of both.
Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease Classification
In this work, we propose Many-MobileNet, an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture.
TPOT: Topology Preserving Optimal Transport in Retinal Fundus Image Enhancement
Retinal fundus photography enhancement is important for diagnosing and monitoring retinal diseases.
A Recipe for Geometry-Aware 3D Mesh Transformers
Utilizing patch-based transformers for unstructured geometric data such as polygon meshes presents significant challenges, primarily due to the absence of a canonical ordering and variations in input sizes.
EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices
The rise of Vision Transformer (ViT) has effectively compensated for this deficiency of CNNs and promoted the application of ViT-based U-networks in medical image segmentation.
STA-Unet: Rethink the semantic redundant for Medical Imaging Segmentation
In particular, deep neural networks based on a U-shaped architecture (UNet) with skip connections have been adopted for several medical imaging tasks, including organ segmentation.
CUNSB-RFIE: Context-aware Unpaired Neural Schr"{o}dinger Bridge in Retinal Fundus Image Enhancement
In this work, we leverage the SB framework to propose an image-to-image translation pipeline for retinal image enhancement.
Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement
Retinal fundus photography offers a non-invasive way to diagnose and monitor a variety of retinal diseases, but is prone to inherent quality glitches arising from systemic imperfections or operator/patient-related factors.
AMG: Avatar Motion Guided Video Generation
Human video generation task has gained significant attention with the advancement of deep generative models.
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification
Second, we propose two mechanisms to enforce the diversity among the global vectors to be more descriptive of the entire bag: (i) positive instance alignment and (ii) a novel, efficient, and theoretically guaranteed diversification learning paradigm.
SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation
Although numerous follow-up studies have also been dedicated to improving the performance of standard UNet, few have conducted in-depth analyses of the underlying interest pattern of UNet in medical image segmentation.
Ranked #17 on
Medical Image Segmentation
on Synapse multi-organ CT
TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC).
Generation of Uncorrelated Residual Variables for Chemical Process Fault Diagnosis via Transfer Learning-based Input-Output Decoupled Network
However, traditional methods exhibit limited effectiveness in modeling high-dimensional nonlinearity and big data, and the decoupling idea has not been well-valued in data-driven frameworks.
Characterizing visual cortical magnification with topological smoothing and optimal transportation
Human vision has different concentration on visual fields.
Reconstructing Retinal Visual Images from 3T fMRI Data Enhanced by Unsupervised Learning
The reconstruction of human visual inputs from brain activity, particularly through functional Magnetic Resonance Imaging (fMRI), holds promising avenues for unraveling the mechanisms of the human visual system.
OmniMotionGPT: Animal Motion Generation with Limited Data
Our paper aims to generate diverse and realistic animal motion sequences from textual descriptions, without a large-scale animal text-motion dataset.
SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image Classification
Typical MIL methods include a feature embedding part, which embeds the instances into features via a pre-trained feature extractor, and an MIL aggregator that combines instance embeddings into predictions.
PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers
Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags.
Multiple Instance Learning
Weakly Supervised Classification
+3
nnMobileNet: Rethinking CNN for Retinopathy Research
Over the past few decades, convolutional neural networks (CNNs) have been at the forefront of the detection and tracking of various retinal diseases (RD).
SFCNeXt: a simple fully convolutional network for effective brain age estimation with small sample size
Deep neural networks (DNN) have been designed to predict the chronological age of a healthy brain from T1-weighted magnetic resonance images (T1 MRIs), and the predicted brain age could serve as a valuable biomarker for the early detection of development-related or aging-related disorders.
A Surface-Based Federated Chow Test Model for Integrating APOE Status, Tau Deposition Measure, and Hippocampal Surface Morphometry
Objective: To build a surface-based model to 1) detect differences between APOE subgroups in patterns of tau deposition and hippocampal atrophy, and 2) use the extracted surface-based features to predict cognitive decline.
TetCNN: Convolutional Neural Networks on Tetrahedral Meshes
Our results show the superiority of our LBO-based convolution layer and adapted pooling over the conventionally used unitary cortical thickness, graph Laplacian, and point cloud representation.
Optimal Transport Guided Unsupervised Learning for Enhancing low-quality Retinal Images
In this paper, we proposed a simple but effective end-to-end framework for enhancing poor-quality retinal fundus images.
OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing
Non-mydriatic retinal color fundus photography (CFP) is widely available due to the advantage of not requiring pupillary dilation, however, is prone to poor quality due to operators, systemic imperfections, or patient-related causes.
Improved Prediction of Beta-Amyloid and Tau Burden Using Hippocampal Surface Multivariate Morphometry Statistics and Sparse Coding
Experimental results suggest that amyloid/tau measurements predicted with our PASCP-MP representations are closer to the real values than the measures derived from other approaches, such as hippocampal surface area, volume, and shape morphometry features based on spherical harmonics (SPHARM).
Anisotropic Multi-Scale Graph Convolutional Network for Dense Shape Correspondence
This paper studies 3D dense shape correspondence, a key shape analysis application in computer vision and graphics.
Self-Supervised Equivariant Regularization Reconciles Multiple Instance Learning: Joint Referable Diabetic Retinopathy Classification and Lesion Segmentation
Lesion appearance is a crucial clue for medical providers to distinguish referable diabetic retinopathy (rDR) from non-referable DR.
OTFPF: Optimal Transport-Based Feature Pyramid Fusion Network for Brain Age Estimation with 3D Overlapped ConvNeXt
In this paper, we propose an end-to-end neural network architecture, referred to as optimal transport based feature pyramid fusion (OTFPF) network, for the brain age estimation with T1 MRIs.
Functional2Structural: Cross-Modality Brain Networks Representation Learning
Since brain networks derived from functional and structural MRI describe the brain topology from different perspectives, exploring a representation that combines these cross-modality brain networks is non-trivial.
Geometry-Aware Hierarchical Bayesian Learning on Manifolds
Furthermore, we incorporate the feature learning of neural networks with the feature aggregation of Bayesian models to investigate the feasibility of jointly learning on manifolds.
Predicting Tau Accumulation in Cerebral Cortex with Multivariate MRI Morphometry Measurements, Sparse Coding, and Correntropy
We evaluate our framework on 925 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI).
Topological Receptive Field Model for Human Retinotopic Mapping
Here we propose a topological receptive field (tRF) model which imposes the topological condition when decoding retinotopic fMRI signals.
Cortical Surface Shape Analysis Based on Alexandrov Polyhedra
Shape analysis has been playing an important role in early diagnosis and prognosis of neurodegenerative diseases such as Alzheimer's diseases (AD).
Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition
With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.
Stochastic Hybrid Combining Design for Quantized Massive MIMO Systems
Both the power-dissipation and cost of massive multiple-input multiple-output (mMIMO) systems may be substantially reduced by using low-resolution analog-to-digital converters (LADCs) at the receivers.
Deep Representation Learning For Multimodal Brain Networks
The higher-order network mappings from brain structural networks to functional networks are learned in the node domain.
Optimizing Visual Cortex Parameterization with Error-Tolerant Teichmuller Map in Retinotopic Mapping
Although we focus on retinotopic mapping, the proposed framework is general and can be applied to process other human sensory maps.
The Alzheimer's Disease Prediction Of Longitudinal Evolution (TADPOLE) Challenge: Results after 1 Year Follow-up
TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease.
Geometric Brain Surface Network For Brain Cortical Parcellation
Our model is a two-stage deep network which contains a coarse parcellation network with a U-shape structure and a refinement network to fine-tune the coarse results.
Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community.
Graph Neural Networks for User Identity Linkage
In particular, we provide a principled approach to jointly capture local and global information in the user-user social graph and propose the framework {\m}, which jointly learning user representations for user identity linkage.
MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
State-of-the-art deep model compression methods exploit the low-rank approximation and sparsity pruning to remove redundant parameters from a learned hidden layer.
Regularized Wasserstein Means for Aligning Distributional Data
We propose to align distributional data from the perspective of Wasserstein means.
Variational Wasserstein Clustering
We propose a new clustering method based on optimal transportation.
Dynamically Hierarchy Revolution: DirNet for Compressing Recurrent Neural Network on Mobile Devices
Recurrent neural networks (RNNs) achieve cutting-edge performance on a variety of problems.
Intrinsic 3D Dynamic Surface Tracking Based on Dynamic Ricci Flow and Teichmuller Map
In this paper, we propose a novel automatic method for non-rigid 3D dynamic surface tracking with surface Ricci flow and Teichmuller map methods.
An Optimal Transportation Based Univariate Neuroimaging Index
We compute the OT from each image to a template and measure the Wasserstein distance between them.
Multi-task Dictionary Learning based Convolutional Neural Network for Computer aided Diagnosis with Longitudinal Images
Firstly, we pre-train CNN on the ImageNet dataset and transfer the knowledge from the pre-trained model to the medical imaging progression representation, generating the features for different tasks.
Large-scale Feature Selection of Risk Genetic Factors for Alzheimer's Disease via Distributed Group Lasso Regression
Then we select the relevant group features by performing the group Lasso feature selection process in a sequence of parameters.
Large-scale Collaborative Imaging Genetics Studies of Risk Genetic Factors for Alzheimer's Disease Across Multiple Institutions
To the best of our knowledge, this is the first successful run of the computationally intensive model selection procedure to learn a consistent model across different institutions without compromising their privacy while ranking the SNPs that may collectively affect AD.
Shape Analysis With Hyperbolic Wasserstein Distance
Experimental results demonstrate that our method may be used as an effective shape index, which outperforms some other standard shape measures in our AD versus healthy control classification study.
Area Preserving Brain Mapping
Experimental results on caudate nucleus surface mapping and cortical surface mapping demonstrate the efficacy and efficiency of the proposed method.
Hyperbolic Harmonic Mapping for Constrained Brain Surface Registration
This work conquer this problem by changing the Riemannian metric on the target surface to a hyperbolic metric, so that the harmonic mapping is guaranteed to be a diffeomorphism under landmark constraints.
